Grok 4 Fast

Released2025-09-19
Price per 1MNot listed
Overall score50.8 (early, few results)
ProviderxAI
WeightsProprietary

Scores

DimensionScoreRankBenchmarks
Overall: Balanced 50.8 4
Overall: Coding 50.7 4
Overall: Reasoning 50.8 3
Overall: Agentic work 50.7 4
Agents 50.7 1
Reasoning 50.8 3

Configurations

ConfigurationBalancedBenchmarks
Unspecified setting 46.5 ±9.2 3
High 50.7 ±6.1 1
Thinking 51.4 ±9.4 1

Evidence

Agents 50.7 ±3.4

BenchmarkResultSourceDate
tau2-bench Banking Knowledge 15.7% tau2-bench 2026-05-05

Reasoning 50.8 ±4.3

BenchmarkResultSourceDate
ARC-AGI-2 5.3% Epoch AI 2026-11-11
ARC-AGI-1 48.5% Epoch AI 2026-11-11
Kagi Reasoning Benchmark 66.1% Kagi 2026-11-11

Results not used in the score

BenchmarkResultSourceWhy not used
Kagi Reasoning Benchmark 35.4% Kagi A stronger configuration result was used

Names matched to this model

grok-4-fast

Compare Grok 4 Fast with other models